{"id":"https://openalex.org/W4321021825","doi":"https://doi.org/10.1109/tcyb.2023.3241015","title":"Inverse Reinforcement Learning for Trajectory Imitation Using Static Output Feedback Control","display_name":"Inverse Reinforcement Learning for Trajectory Imitation Using Static Output Feedback Control","publication_year":2023,"publication_date":"2023-02-16","ids":{"openalex":"https://openalex.org/W4321021825","doi":"https://doi.org/10.1109/tcyb.2023.3241015","pmid":"https://pubmed.ncbi.nlm.nih.gov/37027769"},"language":"en","primary_location":{"id":"doi:10.1109/tcyb.2023.3241015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2023.3241015","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102973745","display_name":"Wenqian Xue","orcid":"https://orcid.org/0000-0002-3670-3854"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]},{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenqian Xue","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001862814","display_name":"Bosen Lian","orcid":"https://orcid.org/0000-0002-3275-9551"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bosen Lian","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033960992","display_name":"Jialu Fan","orcid":"https://orcid.org/0000-0001-7585-1166"},"institutions":[{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]},{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jialu Fan","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042520521","display_name":"Tianyou Chai","orcid":"https://orcid.org/0000-0002-4623-1483"},"institutions":[{"id":"https://openalex.org/I4391767858","display_name":"State Key Laboratory of Synthetical Automation for Process Industries","ror":"https://ror.org/0380ng272","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391767858","https://openalex.org/I9224756"]},{"id":"https://openalex.org/I9224756","display_name":"Northeastern University","ror":"https://ror.org/03awzbc87","country_code":"CN","type":"education","lineage":["https://openalex.org/I9224756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Chai","raw_affiliation_strings":["State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Synthetical Automation for Process Industries and International Joint Research Laboratory of Integrated Automation, Northeastern University, Shenyang, China","institution_ids":["https://openalex.org/I9224756","https://openalex.org/I4391767858"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016137188","display_name":"Frank L. Lewis","orcid":"https://orcid.org/0000-0003-4074-1615"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Frank L. Lewis","raw_affiliation_strings":["UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"UTA Research Institute, University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102973745"],"corresponding_institution_ids":["https://openalex.org/I4391767858","https://openalex.org/I9224756"],"apc_list":null,"apc_paid":null,"fwci":6.6499,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.9734101,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"54","issue":"3","first_page":"1695","last_page":"1707"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9247999787330627,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.693329393863678},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.690606951713562},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6475070118904114},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6259846091270447},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.5084661245346069},{"id":"https://openalex.org/keywords/inverse","display_name":"Inverse","score":0.4831494688987732},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.46807822585105896},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.45608681440353394},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3851384222507477},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3681172728538513},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3566543161869049},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26261019706726074},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20888125896453857}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.693329393863678},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.690606951713562},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6475070118904114},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6259846091270447},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.5084661245346069},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.4831494688987732},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.46807822585105896},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.45608681440353394},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3851384222507477},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3681172728538513},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3566543161869049},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26261019706726074},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20888125896453857},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcyb.2023.3241015","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcyb.2023.3241015","pdf_url":null,"source":{"id":"https://openalex.org/S4210191041","display_name":"IEEE Transactions on Cybernetics","issn_l":"2168-2267","issn":["2168-2267","2168-2275"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cybernetics","raw_type":"journal-article"},{"id":"pmid:37027769","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37027769","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on cybernetics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3239473734","display_name":null,"funder_award_id":"XLYC2007135","funder_id":"https://openalex.org/F4320329895","funder_display_name":"Liaoning Revitalization Talents Program"},{"id":"https://openalex.org/G3474679019","display_name":null,"funder_award_id":"61991400","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4867859608","display_name":null,"funder_award_id":"61991403","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5409562055","display_name":null,"funder_award_id":"B08015","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G5898287775","display_name":null,"funder_award_id":"61991404","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null},{"id":"https://openalex.org/F4320329895","display_name":"Liaoning Revitalization Talents Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1511275238","https://openalex.org/W1603698551","https://openalex.org/W1614417283","https://openalex.org/W1929981607","https://openalex.org/W1970916399","https://openalex.org/W1999874108","https://openalex.org/W2005437559","https://openalex.org/W2006263815","https://openalex.org/W2012451615","https://openalex.org/W2041626001","https://openalex.org/W2050838777","https://openalex.org/W2058627792","https://openalex.org/W2071004621","https://openalex.org/W2086602679","https://openalex.org/W2095590702","https://openalex.org/W2121196039","https://openalex.org/W2144557480","https://openalex.org/W2148439597","https://openalex.org/W2165726932","https://openalex.org/W2484646121","https://openalex.org/W2523345745","https://openalex.org/W2580629550","https://openalex.org/W2592261783","https://openalex.org/W2734548765","https://openalex.org/W2766143943","https://openalex.org/W2771641782","https://openalex.org/W2886285798","https://openalex.org/W2912832158","https://openalex.org/W2942227124","https://openalex.org/W2950989964","https://openalex.org/W2989767232","https://openalex.org/W3088597768","https://openalex.org/W3136946585","https://openalex.org/W3138463803","https://openalex.org/W3156476459","https://openalex.org/W3157144609","https://openalex.org/W3170519291","https://openalex.org/W3195322794","https://openalex.org/W3200276130","https://openalex.org/W3204571453","https://openalex.org/W4214717370","https://openalex.org/W4301018745","https://openalex.org/W4388319978","https://openalex.org/W6640443443","https://openalex.org/W6677631742","https://openalex.org/W6910669261"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4323768008","https://openalex.org/W1941703695","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W3131574667","https://openalex.org/W4391331176"],"abstract_inverted_index":{"This":[0],"article":[1],"studies":[2],"the":[3,34,52,55,58,130],"trajectory":[4],"imitation":[5],"control":[6],"problem":[7],"of":[8,57],"linear":[9],"systems":[10],"suffering":[11],"external":[12],"disturbances":[13],"and":[14,45,49,67,89,118],"develops":[15],"a":[16,86,97,107],"data-driven":[17,98,108],"static":[18,75],"output":[19,50],"feedback":[20],"(OPFB)":[21],"control-based":[22],"inverse":[23,77],"reinforcement":[24],"learning":[25],"(RL)":[26],"approach.":[27],"An":[28],"Expert-Learner":[29],"structure":[30],"is":[31,85,96,106],"considered":[32],"where":[33],"learner":[35,53],"aims":[36],"to":[37,128],"imitate":[38],"expert's":[39,44],"trajectory.":[40,73],"Using":[41],"only":[42,111],"measured":[43],"learner's":[46],"own":[47],"input":[48],"data,":[51],"computes":[54],"policy":[56],"expert":[59],"by":[60],"reconstructing":[61],"its":[62,70],"unknown":[63],"value":[64],"function":[65],"weights":[66],"thus,":[68],"imitates":[69],"optimally":[71],"operating":[72],"Three":[74],"OPFB":[76],"RL":[78],"algorithms":[79],"are":[80,120,126],"proposed.":[81],"The":[82,93,103,114],"first":[83],"algorithm":[84,95,105],"model-based":[87],"scheme":[88],"serves":[90],"as":[91],"basis.":[92],"second":[94],"method":[99,109],"using":[100,110],"input-state":[101],"data.":[102,113],"third":[104],"input-output":[112],"stability,":[115],"convergence,":[116],"optimality,":[117],"robustness":[119],"well":[121],"analyzed.":[122],"Finally,":[123],"simulation":[124],"experiments":[125],"conducted":[127],"verify":[129],"proposed":[131],"algorithms.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":4}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2025-10-10T00:00:00"}